gws-docs-write

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the gws binary to perform document append operations. This is the expected and documented behavior for this tool.
  • [PROMPT_INJECTION]: The skill provides an interface to write user-supplied or agent-generated text into a document. While this represents a surface for indirect prompt injection, the inclusion of a caution for user confirmation before execution acts as a safety checkpoint.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 01:27 PM
Security Audit — agent-trust-hub — gws-docs-write